© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13332
    Prev
    Next
    INDEX
    Explanations

    segments of text involving blockage or obstructions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obstructing
    -1.11
     obstruction
    -0.96
     blocker
    -0.94
     blockers
    -0.83
    parsedMessage
    -0.82
     blocking
    -0.82
    MessageTagHelper
    -0.81
     obstructive
    -0.80
    blocking
    -0.79
    JspWriter
    -0.72
    POSITIVE LOGITS
     blocked
    1.52
     Blocked
    1.27
    blocked
    0.96
    Blocked
    0.89
    werth
    0.52
     gehe
    0.51
    はじめに
    0.50
    üyor
    0.49
    undidad
    0.49
    tolist
    0.48
    Activations Density 0.002%

    No Known Activations